[NeurIPS 2025] Thinkless: LLM Learns When to Think
-
Updated
Sep 26, 2025 - Python
#
hybrid-reasoning
Here are 2 public repositories matching this topic...
FastAPI workbench for text embedding (Gemma-300m with Matryoshka) and summarization (Gemma/Gemini). Features hardware acceleration, caching, and secure endpoints for local LLM integration.
secure-access production-ai code-summarization code-intelligence fastapi text-embeddings local-ai gemma3 rate-limiting-caching hybrid-reasoning multimodel-llm matryoshka-embeddings persona-engineering
-
Updated
Oct 20, 2025 - Python
Improve this page
Add a description, image, and links to the hybrid-reasoning topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the hybrid-reasoning topic, visit your repo's landing page and select "manage topics."